vllm-studio-backend

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The backend architecture described in the skill is designed to process untrusted chat messages while possessing high-privilege tool execution capabilities.
  • Ingestion points: Untrusted user input enters the system via the chat_messages object in the /v1/chat/completions and /chats/:id/turn endpoints (referenced in references/backend-architecture.md).
  • Boundary markers: The documentation does not describe the use of delimiters or boundary markers to isolate untrusted data from instructions within the Pi-mono agent loop.
  • Capability inventory: The system executes tools server-side, including AgentFS (file system access) and MCP (Model Context Protocol), which provide a significant impact if subverted (referenced in SKILL.md and references/backend-architecture.md).
  • Sanitization: There is no mention of sanitization, validation, or filtering of the input data before it is interpolated into the agent's reasoning or tool-calling logic.
  • [Command Execution] (LOW): The skill contains commands for local service management and health monitoring.
  • Evidence: references/backend-commands.md provides shell commands for starting the controller (./start.sh) and performing network tests with curl. These are standard development operations but represent local execution capabilities.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 05:52 AM